Hello, everyone,
I’m new to the field of object detection, and I’m now learning some basics. I found a very helpful tutorial on this website which can be accessed via the link below. The article is about calculating the Histogram of Gradients of an image.
In Step #4 of the approach, it reads: “If we divide the image into 8×8 cells and generate the histograms, we will get a 9 x 1 matrix for each cell.”
I don’t get it how this step is done.
By “8x8 cells”, I guess it means the size of each cell is 8 pixels by 8 pixels. If so, how do we generate the “9 x 1 matrix”? And, what is the meaning of each element in this matrix? Is there any example?
Thanks in advance to anyone who would answer this question for me.
1 post - 1 participant